Spike-Timing Dependent Plasticity in Ultra-Dense Synapse Cross-Bar Arrays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current neuromorphic systems fail to effectively implement spike-timing dependent plasticity in ultra-dense synapse cross-bar arrays, which is crucial for mimicking biological brain functionality, due to limitations in updating rates and conductance modulation.
Innovation Solution
The implementation of a method and system that utilize alert and gate pulses to modulate the conductance of variable state resistors in an ultra-dense cross-bar array, where each electronic neuron sends alert pulses to connected neurons, and the combination of these pulses with response pulses from receiving neurons adjusts the conductance based on the time since the last spiking event, enabling spike-timing dependent plasticity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional neuromorphic systems are used to implement spike-timing dependent plasticity in ultra-dense synapse cross-bar arrays, then the system structure can be maintained, but the update rate is limited and conductance modulation is ineffective
Solution Approach 1:
The patent implements dynamic conductance modulation by making the synapse weight update dependent on the precise timing between pre-synaptic and post-synaptic spikes. The STDP mechanism dynamically adjusts conductance based on temporal relationships rather than using static or uniformly timed updates, enabling both high update rates and effective conductance modulation.
Solution Approach 2:
The patent changes the parameter of conductance modulation by introducing time-dependent weighting factors in the STDP rule. The conductance change is modulated by exponential decay functions of the time delay between spikes, allowing precise control over conductance updates based on spike timing relationships.
2Adaptability or versatility
If the conductance of variable state resistors is modulated using traditional methods, then the system complexity remains manageable, but the ability to mimic biological brain functionality is reduced
Solution Approach 1:
The patent segments the STDP implementation into distinct functional components: alert pulse generation from the pre-synaptic neuron, response pulse generation from the post-synaptic neuron, and conductance modulation at the synapse. This segmentation allows each component to be optimized independently while maintaining overall biological fidelity.
Solution Approach 2:
The patent introduces alert pulses and response pulses as intermediary signals that mediate the interaction between pre-synaptic and post-synaptic neurons. These pulse intermediaries carry timing information across the synapse, enabling STDP without requiring direct complex communication mechanisms between neurons.
3Quantity of substance
If ultra-dense cross-bar arrays are implemented without STDP, then manufacturing density is achieved, but spike-timing dependent plasticity functionality is lost
Solution Approach 1:
The patent implements a universal STDP mechanism that can be applied across all synapses in the ultra-dense cross-bar array through standardized alert and response pulse generation. This universal approach enables STDP functionality throughout the dense array without requiring specialized structures for each synapse, maintaining both high density and functional capability.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach significantly improves update rates to the tens of Gigahertz range and effectively modulates synaptic conductance, enhancing the neuromorphic system's ability to mimic biological brain functionality by implementing spike-timing dependent plasticity.
Implementation Method 1
the combination of the gate pulse and response pulse is capable increasing or decreasing conductance of a variable state resistor
Data Source
AI summary
Embodiments of the invention relate to producing spike-timing dependent plasticity in an ultra-dense synapse cross-bar array for neuromorphic systems. An aspect of the invention includes when an electronic neuron spikes, an alert pulse is sent from the spiking electronic neuron to each electronic neuron connected to the spiking electronic neuron. When the spiking electronic neuron sends the alert pulse, a gate pulse is sent from the spiking electronic neuron to each electronic neuron connected to the spiking electronic neuron. When each electronic neuron receives the alert pulse, a response pulse is sent from each electronic neuron receiving the alert pulse to the spiking electronic neuron. The response pulse is a function of time since a last spiking of the electronic neuron receiving the alert pulse. In addition, the combination of the gate pulse and response pulse is capable increasing or decreasing conductance of a variable state resistor.